Variational autoencoders (VAEs) are powerful deep generative models widely used to
represent high-dimensional complex data through a low-dimensional latent space learned …

The free energy principle, and its corollary active inference, constitute a bio-inspired theory
that assumes biological agents act to remain in a restricted set of preferred states of the …

Score-based generative models (SGMs) have recently demonstrated impressive results in
terms of both sample quality and distribution coverage. However, they are usually applied …

Normalizing flows, autoregressive models, variational autoencoders (VAEs), and deep
energy-based models are among competing likelihood-based frameworks for deep …

Score-based diffusion models synthesize samples by reversing a stochastic process that
diffuses data to noise, and are trained by minimizing a weighted combination of score …

In this paper we propose a new generative model of text, Step-unrolled Denoising
Autoencoder (SUNDAE), that does not rely on autoregressive models. Similarly to denoising …

Abstract Posterior collapse in Variational Autoencoders (VAEs) with uninformative priors
arises when the variational posterior distribution closely matches the prior for a subset of …

Whereas diverse variations of diffusion models exist, extending the linear diffusion into a
nonlinear diffusion process is investigated by very few works. The nonlinearity effect has …

Latent space EBMs, also known as energy-based priors, have drawn growing interests in
the field of generative modeling due to its flexibility in the formulation and strong modeling …

Preference data is a form of dyadic data, with measurements associated with pairs of
elements arising from two discrete sets of objects. These are users and items, as well as …